English

Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation

Computer Vision and Pattern Recognition 2023-02-07 v1 Artificial Intelligence

Abstract

Diffusion models are able to generate photorealistic images in arbitrary scenes. However, when applying diffusion models to image translation, there exists a trade-off between maintaining spatial structure and high-quality content. Besides, existing methods are mainly based on test-time optimization or fine-tuning model for each input image, which are extremely time-consuming for practical applications. To address these issues, we propose a new approach for flexible image translation by learning a layout-aware image condition together with a text condition. Specifically, our method co-encodes images and text into a new domain during the training phase. In the inference stage, we can choose images/text or both as the conditions for each time step, which gives users more flexible control over layout and content. Experimental comparisons of our method with state-of-the-art methods demonstrate our model performs best in both style image translation and semantic image translation and took the shortest time.

Keywords

Cite

@article{arxiv.2302.02284,
  title  = {Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation},
  author = {Shiqi Sun and Shancheng Fang and Qian He and Wei Liu},
  journal= {arXiv preprint arXiv:2302.02284},
  year   = {2023}
}
R2 v1 2026-06-28T08:32:11.714Z